vachonni
/

wav2vec2-large-xls-r-300m-dansk-CV-80

Automatic Speech Recognition

generated_from_trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

vachonni commited on Feb 1, 2022

Commit

85f4ac5

•

1 Parent(s): 223a032

Update README.md

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -14,7 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # wav2vec2-large-xls-r-300m-dansk-CV-80
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
 It achieves the following results on the evaluation set:
 - eval_loss: 0.6394
 - eval_wer: 0.3682
@@ -26,7 +27,7 @@ It achieves the following results on the evaluation set:
 ## Model description
-More information needed
 ## Intended uses & limitations
@@ -34,7 +35,7 @@ More information needed
 ## Training and evaluation data
-More information needed
 ## Training procedure

 # wav2vec2-large-xls-r-300m-dansk-CV-80
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) for Danish, using the [mozilla-foundation/common_voice_8_0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0) dataset.
 It achieves the following results on the evaluation set:
 - eval_loss: 0.6394
 - eval_wer: 0.3682
 ## Model description
+ASR Danish model
 ## Intended uses & limitations
 ## Training and evaluation data
+Danish subset of [mozilla-foundation/common_voice_8_0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0)
 ## Training procedure